https://scholars.lib.ntu.edu.tw/handle/123456789/559426
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.author | Su, S.-Y. | en_US |
dc.contributor.author | Li, X. | en_US |
dc.contributor.author | Gao, J. | en_US |
dc.contributor.author | Liu, J. | en_US |
dc.contributor.author | YUN-NUNG CHEN | en_US |
dc.date.accessioned | 2021-05-05T03:42:57Z | - |
dc.date.available | 2021-05-05T03:42:57Z | - |
dc.date.issued | 2020 | - |
dc.identifier.uri | https://www.scopus.com/inward/record.url?eid=2-s2.0-85062083317&partnerID=40&md5=f4397ee8a77a664510b0b84cbf926754 | - |
dc.identifier.uri | https://scholars.lib.ntu.edu.tw/handle/123456789/559426 | - |
dc.description.abstract | This paper presents a Discriminative Deep Dyna-Q (D3Q) approach to improving the effectiveness and robustness of Deep Dyna-Q (DDQ), a recently proposed framework that extends the Dyna-Q algorithm to integrate planning for task-completion dialogue policy learning. To obviate DDQ's high dependency on the quality of simulated experiences, we incorporate an RNN-based discriminator in D3Q to differentiate simulated experience from real user experience in order to control the quality of training data. Experiments show that D3Q significantly outperforms DDQ by controlling the quality of simulated experience used for planning. The effectiveness and robustness of D3Q is further demonstrated in a domain extension setting, where the agent's capability of adapting to a changing environment is tested.1 © 2018 Association for Computational Linguistics | - |
dc.relation.ispartof | Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 | - |
dc.subject.other | Deep learning; Natural language processing systems; User experience; Changing environment; Domain extensions; Policy learning; Q algorithms; Robust planning; Training data; Quality control | - |
dc.title | Discriminative deep Dyna-Q: Robust planning for dialogue policy learning | en_US |
dc.type | conference paper | en |
dc.identifier.scopus | 2-s2.0-85062083317 | - |
dc.relation.pages | 3813-3823 | - |
item.cerifentitytype | Publications | - |
item.fulltext | no fulltext | - |
item.openairecristype | http://purl.org/coar/resource_type/c_5794 | - |
item.openairetype | conference paper | - |
item.grantfulltext | none | - |
crisitem.author.dept | Networking and Multimedia | - |
crisitem.author.dept | Computer Science and Information Engineering | - |
crisitem.author.dept | FinTech Center | - |
crisitem.author.orcid | 0000-0003-1777-3942 | - |
crisitem.author.parentorg | College of Electrical Engineering and Computer Science | - |
crisitem.author.parentorg | College of Electrical Engineering and Computer Science | - |
crisitem.author.parentorg | Others: University-Level Research Centers | - |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。